User repository on GitHub
- Forks
- 0
- Last pushed
- Updated Sep 2026
Repo stats from the GitHub API, cached Oct 2026.
Jev directory
CommunityJev Demos & Experiments
TC39 Proposal Atlas
Interactive web application that applies Jev's System One paradigm to the live corpus of ECMAScript/TC39 proposals, enriching each one with typed semantic dimensions such as adoption path, cognitive overhead, web-compat risk and architectural signals.
- Stars
- 1
- Language
- TypeScript
- Reading time
- 2 min
- Published by
- Community
- Author
- hemanth
- Last verified
- Oct 2026
Used inJev for Software & DevTools
- Languages
- TypeScript
- Platforms
- Browser
- Capabilities
- Open source
Highlights
- Adds five dimensions per proposal: adoption path, cognitive overhead (Score 1-5), primary motivation, web-compat risk (Score 1-5) and architectural signals.
- Architectural signals ask whether a proposal mutates the prototype chain, introduces new grammar or syntax, or crosses a realm boundary.
- Classifies proposals into 7 foundational intent archetypes; the README reports expressive_composition at 44.1% (143 proposals) with a 33.6% Stage 4 rate.
- Styled as an asymmetric split-screen with a pastel palette keyed to stages 0-4, Lucide icons and an explicit no-emoji policy.
Watch out
Grounded on the truncated README and GitHub metadata reviewed 2026-10-15; the archetype table is cut off partway through the fifth row and the repo lists no license. Archetype shares are the project's own analysis of the live proposal corpus and no benchmark validates the judgments.
Questions about this entry
Short answers drawn from the linked project or page.
An interactive web application that applies Jev's System One paradigm to the live corpus of ECMAScript/TC39 proposals, enriching each proposal with a semantic taxonomy beyond the usual stage, name, description and author metadata.
Five core ones: adoption path as a Choice (userland_polyfillable, build_transpilable, native_engine_required), cognitive overhead and web-compat risk as 1-5 Scores, primary motivation as a Choice, and architectural signals as Multi-Noul questions.
Seven foundational intent archetypes such as expressive_composition (44.1%, 143 proposals, 33.6% Stage 4 rate), standardizing_de_facto, correcting_historical_regrets, framework_enablement and cross_language_parity, which seeks to explain why proposals succeed or stall.
It evaluates each proposal's structural and contextual nuance with System One questions - Choice, Score and Multi-Noul primitives - rather than free-form text, and displays probabilities and ratings in monospace type.
An asymmetric split-screen layout with min-h-100dvh viewport stability, a pastel palette keyed to stages (Stage 4 mint, Stage 3 sky, Stage 2 peach and so on), Plus Jakarta Sans or Geist with JetBrains Mono, and no emojis.
The README excerpt in this digest does not document API keys or setup steps beyond the stack and design guidelines, so treat deployment requirements as unverified. The repo language is TypeScript and no license is listed.
hemanth created and pushed the repository on 2026-09-17. The digest's README is truncated inside the archetype table, so figures for archetypes beyond the rows shown are not verified in this entry.
More Jev resources like this
JevSpeak explores whether a model that cannot generate text can still talk: about 13 parallel Jev decisions per turn become a typed Semantic IR that a deterministic compiler renders in English or Chinese. Live at jevspeak.org.
Jev Demos & Experiments#community#catalog-import#logicrw
Community
mm-sheng/jevspeakTypeScript
mm-sheng/jevspeakTypeScriptA BYOK workbench for practicing Jev concepts without official access: emulates State, Noul, Score and Choice via Groq, OpenAI, Anthropic, Gemini or local Ollama, or runs against native Jev with authorized credentials.
Jev Demos & Experiments#community#catalog-import#logicrw
A Next.js and MUI showcase of Jev classifying Enron-Spam emails: one call asks a Noul spam question, a Choice category question and a Score urgency question at once. Includes a dataset view, a no-key example tab and a stand-alone Python script.
Jev Demos & Experiments#community#catalog-import#logicrw
Community
harsha89/jev-demoTypeScript
harsha89/jev-demoTypeScriptAn AI companion that replies only with facial expressions: Jev judges each message and picks one of 16 moods while blobatar morphs its face, with no text replies and no visible chat history.
Jev Demos & Experiments#community#catalog-import#logicrw
Community
appchainai/jevatarTypeScript
appchainai/jevatarTypeScriptA one-page playground and test bench for TypeSafe Jev: pick a backend, load an example and run typed questions against Jev through OpenRouter or TypeSafe, an LLM baseline, or a keyless mock — all speaking the same /v1/systemone contract, with an inspector for the answer distributions.
Jev Demos & Experiments#community#catalog-import#logicrw
Community
creativoma/here-we-go-jevTypeScript
creativoma/here-we-go-jevTypeScriptA workshop of small, inspectable Python experiments for TypeSafe System One models: ten critical bays, from fraud screening to emergency dispatch, each giving Jev a realistic state while deterministic policy keeps authority over the next action.
Jev Demos & Experiments#community#catalog-import#logicrw
Community
jgalego/jevs-garagePython
jgalego/jevs-garagePythonFrom the Jev guides
Original write-ups on what this entry is for.
From the Jev AI model community
Posts from builders shipping with Jev right now.